Association Rules
Sakina Zaveri
01/10/2020
load the libraries
library(arules)## Warning: package 'arules' was built under R version 3.6.3## Loading required package: Matrix##
## Attaching package: 'arules'## The following objects are masked from 'package:base':
##
## abbreviate, writelibrary(arulesViz)## Warning: package 'arulesViz' was built under R version 3.6.3## Loading required package: grid## Registered S3 method overwritten by 'seriation':
## method from
## reorder.hclust gclusread the data for books!!
books <- read.csv("D:\\DataScience\\Association_Rules\\book.csv")
View(books)
## applying the apriori algo with support = 0.02 and confidence = 0.5
book_rules <- apriori(as.matrix(books) , parameter = list(supp = 0.02 , conf = 0.5 , minlen = 4))## Apriori
##
## Parameter specification:
## confidence minval smax arem aval originalSupport maxtime support minlen
## 0.5 0.1 1 none FALSE TRUE 5 0.02 4
## maxlen target ext
## 10 rules TRUE
##
## Algorithmic control:
## filter tree heap memopt load sort verbose
## 0.1 TRUE TRUE FALSE TRUE 2 TRUE
##
## Absolute minimum support count: 40
##
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[11 item(s), 2000 transaction(s)] done [0.00s].
## sorting and recoding items ... [11 item(s)] done [0.00s].
## creating transaction tree ... done [0.00s].
## checking subsets of size 1 2 3 4 5 6 done [0.00s].
## writing ... [455 rule(s)] done [0.00s].
## creating S4 object ... done [0.00s].head(quality(sort(book_rules,by="lift")))## support confidence coverage lift count
## 16 0.0250 0.6849315 0.0365 14.12230 50
## 278 0.0250 0.6849315 0.0365 14.12230 50
## 20 0.0240 0.6666667 0.0360 13.74570 48
## 283 0.0240 0.6666667 0.0360 13.74570 48
## 28 0.0375 0.6637168 0.0565 13.68488 75
## 24 0.0285 0.6263736 0.0455 12.91492 57## inspecting the data by lift
inspect(tail(sort(book_rules , by="lift")))## lhs rhs support confidence coverage
## [1] {ArtBks,GeogBks,Florence} => {CookBks} 0.023 0.7666667 0.0300
## [2] {CookBks,DoItYBks,ItalArt} => {ChildBks} 0.020 0.7407407 0.0270
## [3] {CookBks,DoItYBks,ArtBks,ItalArt} => {ChildBks} 0.020 0.7407407 0.0270
## [4] {DoItYBks,ArtBks,ItalArt} => {ChildBks} 0.022 0.7333333 0.0300
## [5] {ChildBks,ArtBks,Florence} => {CookBks} 0.025 0.7462687 0.0335
## [6] {CookBks,ArtBks,ItalArt} => {ChildBks} 0.030 0.7317073 0.0410
## lift count
## [1] 1.778809 46
## [2] 1.751160 40
## [3] 1.751160 40
## [4] 1.733649 44
## [5] 1.731482 50
## [6] 1.729805 60## plotting the graph with the help of lift to see support and confidence for each item.
plot(book_rules , jitter = 0 ,by="lift")## Warning: Unknown control parameters: by## Available control parameters (with default values):
## main = Scatter plot for 455 rules
## engine = default
## pch = 19
## cex = 0.5
## xlim = NULL
## ylim = NULL
## zlim = NULL
## alpha = NULL
## col = c("#EE0000FF", "#EE0303FF", "#EE0606FF", "#EE0909FF", "#EE0C0CFF", "#EE0F0FFF", "#EE1212FF", "#EE1515FF", "#EE1818FF", "#EE1B1BFF", "#EE1E1EFF", "#EE2222FF", "#EE2525FF", "#EE2828FF", "#EE2B2BFF", "#EE2E2EFF", "#EE3131FF", "#EE3434FF", "#EE3737FF", "#EE3A3AFF", "#EE3D3DFF", "#EE4040FF", "#EE4444FF", "#EE4747FF", "#EE4A4AFF", "#EE4D4DFF", "#EE5050FF", "#EE5353FF", "#EE5656FF", "#EE5959FF", "#EE5C5CFF", "#EE5F5FFF", "#EE6262FF", "#EE6666FF", "#EE6969FF", "#EE6C6CFF", "#EE6F6FFF", "#EE7272FF", "#EE7575FF", "#EE7878FF", "#EE7B7BFF", "#EE7E7EFF", "#EE8181FF", "#EE8484FF", "#EE8888FF", "#EE8B8BFF", "#EE8E8EFF", "#EE9191FF", "#EE9494FF", "#EE9797FF", "#EE9999FF", "#EE9B9BFF", "#EE9D9DFF", "#EE9F9FFF", "#EEA0A0FF", "#EEA2A2FF", "#EEA4A4FF", "#EEA5A5FF", "#EEA7A7FF", "#EEA9A9FF", "#EEABABFF", "#EEACACFF", "#EEAEAEFF", "#EEB0B0FF", "#EEB1B1FF", "#EEB3B3FF", "#EEB5B5FF", "#EEB7B7FF", "#EEB8B8FF", "#EEBABAFF", "#EEBCBCFF", "#EEBDBDFF", "#EEBFBFFF", "#EEC1C1FF", "#EEC3C3FF", "#EEC4C4FF", "#EEC6C6FF", "#EEC8C8FF", "#EEC9C9FF", "#EECBCBFF", "#EECDCDFF", "#EECFCFFF", "#EED0D0FF", "#EED2D2FF", "#EED4D4FF", "#EED5D5FF", "#EED7D7FF", "#EED9D9FF", "#EEDBDBFF", "#EEDCDCFF", "#EEDEDEFF", "#EEE0E0FF", "#EEE1E1FF", "#EEE3E3FF", "#EEE5E5FF", "#EEE7E7FF", "#EEE8E8FF", "#EEEAEAFF", "#EEECECFF", "#EEEEEEFF")
## newpage = TRUE
## jitter = NA
## verbose = FALSE
## gives the better detailing of the graph.
plotly_arules(book_rules,jitter=0)## Warning: 'plotly_arules' is deprecated.
## Use 'plot' instead.
## See help("Deprecated")## for better visualization and understanding
plot(book_rules , method = "grouped")
plot(book_rules , method = "scatterplot")## To reduce overplotting, jitter is added! Use jitter = 0 to prevent jitter.
plot(book_rules , method = "graph")## Warning: plot: Too many rules supplied. Only plotting the best 100 rules using
## 'support' (change control parameter max if needed)
## applying the apriori algo with support = 0.04 and confidence = 0.7
book_rules1 <- apriori(as.matrix(books) , parameter = list(supp = 0.04 , conf = 0.7 , minlen = 3))## Apriori
##
## Parameter specification:
## confidence minval smax arem aval originalSupport maxtime support minlen
## 0.7 0.1 1 none FALSE TRUE 5 0.04 3
## maxlen target ext
## 10 rules TRUE
##
## Algorithmic control:
## filter tree heap memopt load sort verbose
## 0.1 TRUE TRUE FALSE TRUE 2 TRUE
##
## Absolute minimum support count: 80
##
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[11 item(s), 2000 transaction(s)] done [0.00s].
## sorting and recoding items ... [10 item(s)] done [0.00s].
## creating transaction tree ... done [0.00s].
## checking subsets of size 1 2 3 4 5 done [0.00s].
## writing ... [109 rule(s)] done [0.00s].
## creating S4 object ... done [0.00s].head(quality(sort(book_rules1,by="lift")))## support confidence coverage lift count
## 2 0.0410 1 0.0410 4.149378 82
## 4 0.0465 1 0.0465 2.320186 93
## 6 0.0590 1 0.0590 2.320186 118
## 8 0.0565 1 0.0565 2.320186 113
## 10 0.0585 1 0.0585 2.320186 117
## 12 0.0640 1 0.0640 2.320186 128## inspecting the data by lift
inspect(tail(sort(book_rules1 , by="lift")))## lhs rhs support confidence coverage lift
## [1] {RefBks,ArtBks} => {CookBks} 0.0700 0.7821229 0.0895 1.814670
## [2] {ChildBks,YouthBks} => {CookBks} 0.1290 0.7818182 0.1650 1.813963
## [3] {ChildBks,ArtBks} => {CookBks} 0.1265 0.7784615 0.1625 1.806175
## [4] {CookBks,ArtBks} => {ChildBks} 0.1265 0.7574850 0.1670 1.790745
## [5] {ChildBks,GeogBks} => {CookBks} 0.1495 0.7666667 0.1950 1.778809
## [6] {CookBks,ItalCook} => {ChildBks} 0.0850 0.7488987 0.1135 1.770446
## count
## [1] 140
## [2] 258
## [3] 253
## [4] 253
## [5] 299
## [6] 170## plotting the graph with the help of lift to see support and confidence for each item.
plot(book_rules1 , jitter = 0 ,by="lift")## Warning: Unknown control parameters: by## Available control parameters (with default values):
## main = Scatter plot for 109 rules
## engine = default
## pch = 19
## cex = 0.5
## xlim = NULL
## ylim = NULL
## zlim = NULL
## alpha = NULL
## col = c("#EE0000FF", "#EE0303FF", "#EE0606FF", "#EE0909FF", "#EE0C0CFF", "#EE0F0FFF", "#EE1212FF", "#EE1515FF", "#EE1818FF", "#EE1B1BFF", "#EE1E1EFF", "#EE2222FF", "#EE2525FF", "#EE2828FF", "#EE2B2BFF", "#EE2E2EFF", "#EE3131FF", "#EE3434FF", "#EE3737FF", "#EE3A3AFF", "#EE3D3DFF", "#EE4040FF", "#EE4444FF", "#EE4747FF", "#EE4A4AFF", "#EE4D4DFF", "#EE5050FF", "#EE5353FF", "#EE5656FF", "#EE5959FF", "#EE5C5CFF", "#EE5F5FFF", "#EE6262FF", "#EE6666FF", "#EE6969FF", "#EE6C6CFF", "#EE6F6FFF", "#EE7272FF", "#EE7575FF", "#EE7878FF", "#EE7B7BFF", "#EE7E7EFF", "#EE8181FF", "#EE8484FF", "#EE8888FF", "#EE8B8BFF", "#EE8E8EFF", "#EE9191FF", "#EE9494FF", "#EE9797FF", "#EE9999FF", "#EE9B9BFF", "#EE9D9DFF", "#EE9F9FFF", "#EEA0A0FF", "#EEA2A2FF", "#EEA4A4FF", "#EEA5A5FF", "#EEA7A7FF", "#EEA9A9FF", "#EEABABFF", "#EEACACFF", "#EEAEAEFF", "#EEB0B0FF", "#EEB1B1FF", "#EEB3B3FF", "#EEB5B5FF", "#EEB7B7FF", "#EEB8B8FF", "#EEBABAFF", "#EEBCBCFF", "#EEBDBDFF", "#EEBFBFFF", "#EEC1C1FF", "#EEC3C3FF", "#EEC4C4FF", "#EEC6C6FF", "#EEC8C8FF", "#EEC9C9FF", "#EECBCBFF", "#EECDCDFF", "#EECFCFFF", "#EED0D0FF", "#EED2D2FF", "#EED4D4FF", "#EED5D5FF", "#EED7D7FF", "#EED9D9FF", "#EEDBDBFF", "#EEDCDCFF", "#EEDEDEFF", "#EEE0E0FF", "#EEE1E1FF", "#EEE3E3FF", "#EEE5E5FF", "#EEE7E7FF", "#EEE8E8FF", "#EEEAEAFF", "#EEECECFF", "#EEEEEEFF")
## newpage = TRUE
## jitter = NA
## verbose = FALSE
## gives the better detailing of the graph.
plotly_arules(book_rules1,jitter=0)## Warning: 'plotly_arules' is deprecated.
## Use 'plot' instead.
## See help("Deprecated")## for better visualization and understanding
plot(book_rules1 , method = "grouped")
plot(book_rules1 , method = "scatterplot")## To reduce overplotting, jitter is added! Use jitter = 0 to prevent jitter.
plot(book_rules1 , method = "graph")## Warning: plot: Too many rules supplied. Only plotting the best 100 rules using
## 'support' (change control parameter max if needed)
read the data for movies!!
movies <- read.csv("D:\\DataScience\\Association_Rules\\my_movies.csv",header = TRUE)
View(movies)
movies <- movies[,6:15]
## applying the apriori algo with support = 0.02 and confidence = 0.2
mov_rules <- apriori(as.matrix(movies) , parameter = list(supp = 0.02 , conf = 0.5 , minlen = 3))## Apriori
##
## Parameter specification:
## confidence minval smax arem aval originalSupport maxtime support minlen
## 0.5 0.1 1 none FALSE TRUE 5 0.02 3
## maxlen target ext
## 10 rules TRUE
##
## Algorithmic control:
## filter tree heap memopt load sort verbose
## 0.1 TRUE TRUE FALSE TRUE 2 TRUE
##
## Absolute minimum support count: 0
##
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[10 item(s), 10 transaction(s)] done [0.00s].
## sorting and recoding items ... [10 item(s)] done [0.00s].
## creating transaction tree ... done [0.00s].
## checking subsets of size 1 2 3 4 5 done [0.00s].
## writing ... [74 rule(s)] done [0.00s].
## creating S4 object ... done [0.00s].head(quality(sort(mov_rules,by="lift")))## support confidence coverage lift count
## 5 0.1 1.0 0.1 10 1
## 49 0.1 1.0 0.1 10 1
## 4 0.1 1.0 0.1 5 1
## 7 0.1 1.0 0.1 5 1
## 8 0.1 0.5 0.2 5 1
## 11 0.1 1.0 0.1 5 1## inspecting the data by lift
inspect(head(sort(mov_rules , by="lift")))## lhs rhs support confidence
## [1] {Gladiator,Green.Mile} => {LOTR} 0.1 1.0
## [2] {Sixth.Sense,Gladiator,Green.Mile} => {LOTR} 0.1 1.0
## [3] {Gladiator,LOTR} => {Green.Mile} 0.1 1.0
## [4] {Sixth.Sense,LOTR} => {Green.Mile} 0.1 1.0
## [5] {Sixth.Sense,Green.Mile} => {LOTR} 0.1 0.5
## [6] {LOTR1,Harry.Potter1} => {LOTR2} 0.1 1.0
## coverage lift count
## [1] 0.1 10 1
## [2] 0.1 10 1
## [3] 0.1 5 1
## [4] 0.1 5 1
## [5] 0.2 5 1
## [6] 0.1 5 1## gives the better detailing of the graph.
plotly_arules(mov_rules,jitter=0)## Warning: 'plotly_arules' is deprecated.
## Use 'plot' instead.
## See help("Deprecated")## for better visualization and understanding
plot(mov_rules , jitter = 0 ,by="lift")## Warning: Unknown control parameters: by## Available control parameters (with default values):
## main = Scatter plot for 74 rules
## engine = default
## pch = 19
## cex = 0.5
## xlim = NULL
## ylim = NULL
## zlim = NULL
## alpha = NULL
## col = c("#EE0000FF", "#EE0303FF", "#EE0606FF", "#EE0909FF", "#EE0C0CFF", "#EE0F0FFF", "#EE1212FF", "#EE1515FF", "#EE1818FF", "#EE1B1BFF", "#EE1E1EFF", "#EE2222FF", "#EE2525FF", "#EE2828FF", "#EE2B2BFF", "#EE2E2EFF", "#EE3131FF", "#EE3434FF", "#EE3737FF", "#EE3A3AFF", "#EE3D3DFF", "#EE4040FF", "#EE4444FF", "#EE4747FF", "#EE4A4AFF", "#EE4D4DFF", "#EE5050FF", "#EE5353FF", "#EE5656FF", "#EE5959FF", "#EE5C5CFF", "#EE5F5FFF", "#EE6262FF", "#EE6666FF", "#EE6969FF", "#EE6C6CFF", "#EE6F6FFF", "#EE7272FF", "#EE7575FF", "#EE7878FF", "#EE7B7BFF", "#EE7E7EFF", "#EE8181FF", "#EE8484FF", "#EE8888FF", "#EE8B8BFF", "#EE8E8EFF", "#EE9191FF", "#EE9494FF", "#EE9797FF", "#EE9999FF", "#EE9B9BFF", "#EE9D9DFF", "#EE9F9FFF", "#EEA0A0FF", "#EEA2A2FF", "#EEA4A4FF", "#EEA5A5FF", "#EEA7A7FF", "#EEA9A9FF", "#EEABABFF", "#EEACACFF", "#EEAEAEFF", "#EEB0B0FF", "#EEB1B1FF", "#EEB3B3FF", "#EEB5B5FF", "#EEB7B7FF", "#EEB8B8FF", "#EEBABAFF", "#EEBCBCFF", "#EEBDBDFF", "#EEBFBFFF", "#EEC1C1FF", "#EEC3C3FF", "#EEC4C4FF", "#EEC6C6FF", "#EEC8C8FF", "#EEC9C9FF", "#EECBCBFF", "#EECDCDFF", "#EECFCFFF", "#EED0D0FF", "#EED2D2FF", "#EED4D4FF", "#EED5D5FF", "#EED7D7FF", "#EED9D9FF", "#EEDBDBFF", "#EEDCDCFF", "#EEDEDEFF", "#EEE0E0FF", "#EEE1E1FF", "#EEE3E3FF", "#EEE5E5FF", "#EEE7E7FF", "#EEE8E8FF", "#EEEAEAFF", "#EEECECFF", "#EEEEEEFF")
## newpage = TRUE
## jitter = NA
## verbose = FALSE
plot(mov_rules , method = "grouped")
plot(mov_rules , method = "scatterplot")## To reduce overplotting, jitter is added! Use jitter = 0 to prevent jitter.
plot(mov_rules , method = "graph")
## applying the apriori algo with support = 0.05 and confidence = 0.7
mov_rules1 <- apriori(as.matrix(movies) , parameter = list(supp = 0.05 , conf = 0.7 , minlen = 4))## Apriori
##
## Parameter specification:
## confidence minval smax arem aval originalSupport maxtime support minlen
## 0.7 0.1 1 none FALSE TRUE 5 0.05 4
## maxlen target ext
## 10 rules TRUE
##
## Algorithmic control:
## filter tree heap memopt load sort verbose
## 0.1 TRUE TRUE FALSE TRUE 2 TRUE
##
## Absolute minimum support count: 0
##
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[10 item(s), 10 transaction(s)] done [0.00s].
## sorting and recoding items ... [10 item(s)] done [0.00s].
## creating transaction tree ... done [0.00s].
## checking subsets of size 1 2 3 4 5 done [0.00s].
## writing ... [29 rule(s)] done [0.00s].
## creating S4 object ... done [0.00s].head(quality(sort(mov_rules1,by="lift")))## support confidence coverage lift count
## 4 0.1 1 0.1 10 1
## 3 0.1 1 0.1 5 1
## 5 0.1 1 0.1 5 1
## 6 0.1 1 0.1 5 1
## 7 0.1 1 0.1 5 1
## 8 0.1 1 0.1 5 1## inspecting the data by lift
inspect(head(sort(mov_rules1 , by="lift")))## lhs rhs support confidence
## [1] {Sixth.Sense,Gladiator,Green.Mile} => {LOTR} 0.1 1
## [2] {Sixth.Sense,Gladiator,LOTR} => {Green.Mile} 0.1 1
## [3] {LOTR1,Harry.Potter1,LOTR2} => {Green.Mile} 0.1 1
## [4] {LOTR1,Harry.Potter1,Green.Mile} => {LOTR2} 0.1 1
## [5] {LOTR1,LOTR2,Green.Mile} => {Harry.Potter1} 0.1 1
## [6] {Harry.Potter1,LOTR2,Green.Mile} => {LOTR1} 0.1 1
## coverage lift count
## [1] 0.1 10 1
## [2] 0.1 5 1
## [3] 0.1 5 1
## [4] 0.1 5 1
## [5] 0.1 5 1
## [6] 0.1 5 1## gives the better detailing of the graph.
plotly_arules(mov_rules1,jitter=0)## Warning: 'plotly_arules' is deprecated.
## Use 'plot' instead.
## See help("Deprecated")## for better visualization and understanding
plot(mov_rules1 , jitter = 0 ,by="lift")## Warning: Unknown control parameters: by## Available control parameters (with default values):
## main = Scatter plot for 29 rules
## engine = default
## pch = 19
## cex = 0.5
## xlim = NULL
## ylim = NULL
## zlim = NULL
## alpha = NULL
## col = c("#EE0000FF", "#EE0303FF", "#EE0606FF", "#EE0909FF", "#EE0C0CFF", "#EE0F0FFF", "#EE1212FF", "#EE1515FF", "#EE1818FF", "#EE1B1BFF", "#EE1E1EFF", "#EE2222FF", "#EE2525FF", "#EE2828FF", "#EE2B2BFF", "#EE2E2EFF", "#EE3131FF", "#EE3434FF", "#EE3737FF", "#EE3A3AFF", "#EE3D3DFF", "#EE4040FF", "#EE4444FF", "#EE4747FF", "#EE4A4AFF", "#EE4D4DFF", "#EE5050FF", "#EE5353FF", "#EE5656FF", "#EE5959FF", "#EE5C5CFF", "#EE5F5FFF", "#EE6262FF", "#EE6666FF", "#EE6969FF", "#EE6C6CFF", "#EE6F6FFF", "#EE7272FF", "#EE7575FF", "#EE7878FF", "#EE7B7BFF", "#EE7E7EFF", "#EE8181FF", "#EE8484FF", "#EE8888FF", "#EE8B8BFF", "#EE8E8EFF", "#EE9191FF", "#EE9494FF", "#EE9797FF", "#EE9999FF", "#EE9B9BFF", "#EE9D9DFF", "#EE9F9FFF", "#EEA0A0FF", "#EEA2A2FF", "#EEA4A4FF", "#EEA5A5FF", "#EEA7A7FF", "#EEA9A9FF", "#EEABABFF", "#EEACACFF", "#EEAEAEFF", "#EEB0B0FF", "#EEB1B1FF", "#EEB3B3FF", "#EEB5B5FF", "#EEB7B7FF", "#EEB8B8FF", "#EEBABAFF", "#EEBCBCFF", "#EEBDBDFF", "#EEBFBFFF", "#EEC1C1FF", "#EEC3C3FF", "#EEC4C4FF", "#EEC6C6FF", "#EEC8C8FF", "#EEC9C9FF", "#EECBCBFF", "#EECDCDFF", "#EECFCFFF", "#EED0D0FF", "#EED2D2FF", "#EED4D4FF", "#EED5D5FF", "#EED7D7FF", "#EED9D9FF", "#EEDBDBFF", "#EEDCDCFF", "#EEDEDEFF", "#EEE0E0FF", "#EEE1E1FF", "#EEE3E3FF", "#EEE5E5FF", "#EEE7E7FF", "#EEE8E8FF", "#EEEAEAFF", "#EEECECFF", "#EEEEEEFF")
## newpage = TRUE
## jitter = NA
## verbose = FALSE
plot(mov_rules1, method = "grouped")
plot(mov_rules1 , method = "scatterplot")## To reduce overplotting, jitter is added! Use jitter = 0 to prevent jitter.
plot(mov_rules1 , method = "graph")
read the data for groceries !!
grocery <- read.transactions("D:\\DataScience\\Association_Rules\\groceries.csv",format = "basket", sep = ",")
## inspecting the data by lift
inspect(grocery[1:5])## items
## [1] {citrus fruit,
## margarine,
## ready soups,
## semi-finished bread}
## [2] {coffee,
## tropical fruit,
## yogurt}
## [3] {whole milk}
## [4] {cream cheese,
## meat spreads,
## pip fruit,
## yogurt}
## [5] {condensed milk,
## long life bakery product,
## other vegetables,
## whole milk}grocery@itemInfo## labels
## 1 abrasive cleaner
## 2 artif. sweetener
## 3 baby cosmetics
## 4 baby food
## 5 bags
## 6 baking powder
## 7 bathroom cleaner
## 8 beef
## 9 berries
## 10 beverages
## 11 bottled beer
## 12 bottled water
## 13 brandy
## 14 brown bread
## 15 butter
## 16 butter milk
## 17 cake bar
## 18 candles
## 19 candy
## 20 canned beer
## 21 canned fish
## 22 canned fruit
## 23 canned vegetables
## 24 cat food
## 25 cereals
## 26 chewing gum
## 27 chicken
## 28 chocolate
## 29 chocolate marshmallow
## 30 citrus fruit
## 31 cleaner
## 32 cling film/bags
## 33 cocoa drinks
## 34 coffee
## 35 condensed milk
## 36 cooking chocolate
## 37 cookware
## 38 cream
## 39 cream cheese
## 40 curd
## 41 curd cheese
## 42 decalcifier
## 43 dental care
## 44 dessert
## 45 detergent
## 46 dish cleaner
## 47 dishes
## 48 dog food
## 49 domestic eggs
## 50 female sanitary products
## 51 finished products
## 52 fish
## 53 flour
## 54 flower (seeds)
## 55 flower soil/fertilizer
## 56 frankfurter
## 57 frozen chicken
## 58 frozen dessert
## 59 frozen fish
## 60 frozen fruits
## 61 frozen meals
## 62 frozen potato products
## 63 frozen vegetables
## 64 fruit/vegetable juice
## 65 grapes
## 66 hair spray
## 67 ham
## 68 hamburger meat
## 69 hard cheese
## 70 herbs
## 71 honey
## 72 house keeping products
## 73 hygiene articles
## 74 ice cream
## 75 instant coffee
## 76 Instant food products
## 77 jam
## 78 ketchup
## 79 kitchen towels
## 80 kitchen utensil
## 81 light bulbs
## 82 liqueur
## 83 liquor
## 84 liquor (appetizer)
## 85 liver loaf
## 86 long life bakery product
## 87 make up remover
## 88 male cosmetics
## 89 margarine
## 90 mayonnaise
## 91 meat
## 92 meat spreads
## 93 misc. beverages
## 94 mustard
## 95 napkins
## 96 newspapers
## 97 nut snack
## 98 nuts/prunes
## 99 oil
## 100 onions
## 101 organic products
## 102 organic sausage
## 103 other vegetables
## 104 packaged fruit/vegetables
## 105 pasta
## 106 pastry
## 107 pet care
## 108 photo/film
## 109 pickled vegetables
## 110 pip fruit
## 111 popcorn
## 112 pork
## 113 pot plants
## 114 potato products
## 115 preservation products
## 116 processed cheese
## 117 prosecco
## 118 pudding powder
## 119 ready soups
## 120 red/blush wine
## 121 rice
## 122 roll products
## 123 rolls/buns
## 124 root vegetables
## 125 rubbing alcohol
## 126 rum
## 127 salad dressing
## 128 salt
## 129 salty snack
## 130 sauces
## 131 sausage
## 132 seasonal products
## 133 semi-finished bread
## 134 shopping bags
## 135 skin care
## 136 sliced cheese
## 137 snack products
## 138 soap
## 139 soda
## 140 soft cheese
## 141 softener
## 142 sound storage medium
## 143 soups
## 144 sparkling wine
## 145 specialty bar
## 146 specialty cheese
## 147 specialty chocolate
## 148 specialty fat
## 149 specialty vegetables
## 150 spices
## 151 spread cheese
## 152 sugar
## 153 sweet spreads
## 154 syrup
## 155 tea
## 156 tidbits
## 157 toilet cleaner
## 158 tropical fruit
## 159 turkey
## 160 UHT-milk
## 161 vinegar
## 162 waffles
## 163 whipped/sour cream
## 164 whisky
## 165 white bread
## 166 white wine
## 167 whole milk
## 168 yogurt
## 169 zwieback## how many items are frequently been purchased by the customer it shows the graph.
itemFrequencyPlot(x=grocery,topN=10)
## applying the apriori algo with support = 0.005 and confidence = 0.5
gro_rules <- apriori(grocery , parameter = list(supp = 0.005 , conf = 0.5 , minlen = 2))## Apriori
##
## Parameter specification:
## confidence minval smax arem aval originalSupport maxtime support minlen
## 0.5 0.1 1 none FALSE TRUE 5 0.005 2
## maxlen target ext
## 10 rules TRUE
##
## Algorithmic control:
## filter tree heap memopt load sort verbose
## 0.1 TRUE TRUE FALSE TRUE 2 TRUE
##
## Absolute minimum support count: 49
##
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[169 item(s), 9835 transaction(s)] done [0.02s].
## sorting and recoding items ... [120 item(s)] done [0.00s].
## creating transaction tree ... done [0.01s].
## checking subsets of size 1 2 3 4 done [0.01s].
## writing ... [120 rule(s)] done [0.00s].
## creating S4 object ... done [0.00s].plot(gro_rules , method = "grouped matrix")
## gives the better detailing of the graph for easy understanding.
plotly_arules(gro_rules,jitter=0)## Warning: 'plotly_arules' is deprecated.
## Use 'plot' instead.
## See help("Deprecated")## applying the apriori algo with support = 0.002 and confidence = 0.6
gro_rules1 <- apriori(grocery , parameter = list(supp = 0.002 , conf = 0.6 , minlen = 4))## Apriori
##
## Parameter specification:
## confidence minval smax arem aval originalSupport maxtime support minlen
## 0.6 0.1 1 none FALSE TRUE 5 0.002 4
## maxlen target ext
## 10 rules TRUE
##
## Algorithmic control:
## filter tree heap memopt load sort verbose
## 0.1 TRUE TRUE FALSE TRUE 2 TRUE
##
## Absolute minimum support count: 19
##
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[169 item(s), 9835 transaction(s)] done [0.01s].
## sorting and recoding items ... [147 item(s)] done [0.00s].
## creating transaction tree ... done [0.00s].
## checking subsets of size 1 2 3 4 5 done [0.01s].
## writing ... [238 rule(s)] done [0.00s].
## creating S4 object ... done [0.00s].plot(gro_rules1 , method = "grouped matrix")
## gives the better detailing of the graph for easy understanding.
plotly_arules(gro_rules1,jitter=0)## Warning: 'plotly_arules' is deprecated.
## Use 'plot' instead.
## See help("Deprecated")Conclusion
changing the support , confidence and length value will give us the different aspect view on the data and can come upto a conclusion.